Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6790. Min Act: -0.1700

Data Index: 7674510 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6873. Min Act: -0.1700

Data Index: 556285 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6925. Min Act: -0.1700

Data Index: 2662043 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6398. Min Act: -0.1700

Data Index: 8746945 (Open Web Text)

Max Activating Token Index: 690

Text #4

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6707. Min Act: -0.1700

Data Index: 6173491 (Open Web Text)

Max Activating Token Index: 670

Text #5

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6663. Min Act: -0.1700

Data Index: 5013510 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6576. Min Act: -0.1700

Data Index: 3706387 (Open Web Text)

Max Activating Token Index: 672

Text #7

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6290. Min Act: -0.1700

Data Index: 2531353 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6277. Min Act: -0.1700

Data Index: 1082176 (Open Web Text)

Max Activating Token Index: 514

Text #9

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6422. Min Act: -0.1700

Data Index: 8513631 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5781. Min Act: -0.1700

Data Index: 4990240 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5852. Min Act: -0.1700

Data Index: 3622230 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.6150. Min Act: -0.1700

Data Index: 3146496 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5764. Min Act: -0.1700

Data Index: 1868474 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5766. Min Act: -0.1700

Data Index: 8730741 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5428. Min Act: -0.1700

Data Index: 335902 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5728. Min Act: -0.1700

Data Index: 2901094 (Open Web Text)

Max Activating Token Index: 445

Text #17

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5836. Min Act: -0.1700

Data Index: 6053536 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5655. Min Act: -0.1700

Data Index: 6743569 (Open Web Text)

Max Activating Token Index: 950

Text #19

Max Range: 4.6925. Min Range: -4.6925

Max Act: 4.5585. Min Act: -0.1700

Data Index: 1711447 (Open Web Text)

Max Activating Token Index: 542